DEV Community

Machine Learning

A branch of artificial intelligence (AI) and computer science which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
A transformer block is six tensors and a bus: read it like a pipeline

A transformer block is six tensors and a bus: read it like a pipeline

Comments
10 min read
From 48M Records to Top 8 Finalists: How We Built an End-to-End Urban Flow AI

From 48M Records to Top 8 Finalists: How We Built an End-to-End Urban Flow AI

Comments 3
5 min read
I Built the SQLite of Vector Search in ~120KB of Pure C & SIMD: 3,000x Faster Cold Starts and Zero Dependencies for AI Agents

I Built the SQLite of Vector Search in ~120KB of Pure C & SIMD: 3,000x Faster Cold Starts and Zero Dependencies for AI Agents

Comments
4 min read
You might not need embeddings: "More Like This" document similarity in pure Python

You might not need embeddings: "More Like This" document similarity in pure Python

Comments
4 min read
What If a Transformer Never Had to Forget? Meet the Recurrent Looped Transformer (RLT)

What If a Transformer Never Had to Forget? Meet the Recurrent Looped Transformer (RLT)

2
Comments
7 min read
Can Your Smartphone Detect Aggressive Driving? Building a ConvLSTM with Sensor Data

Can Your Smartphone Detect Aggressive Driving? Building a ConvLSTM with Sensor Data

Comments
5 min read
Unified driving foundation keeps language skills

Unified driving foundation keeps language skills

Comments
2 min read
MTP in Practice: Benchmarking Gemma's Speculative Decoding on a Real GPU

MTP in Practice: Benchmarking Gemma's Speculative Decoding on a Real GPU

Comments
13 min read
GLM-5.3: The Post-Training Revolution That's Reshaping AI Development

GLM-5.3: The Post-Training Revolution That's Reshaping AI Development

Comments
4 min read
Blog #3: The Beginning of AI Learning

Blog #3: The Beginning of AI Learning

Comments
3 min read
How We Cut Target Leakage from 92% to 0.1% in Court Outcome Prediction (and Built a Triple-A MCP Server)

How We Cut Target Leakage from 92% to 0.1% in Court Outcome Prediction (and Built a Triple-A MCP Server)

Comments
2 min read
Flutter AI waste classification app: On-Device for bank-sampah

Flutter AI waste classification app: On-Device for bank-sampah

Comments
9 min read
My custom filter showed "zero false positives"! Then I realized my validation logic was flawed, letting all the garbage through.

My custom filter showed "zero false positives"! Then I realized my validation logic was flawed, letting all the garbage through.

Comments
4 min read
Pocket Data Science II: Tackling Kaggle Spaceship Titanic on Android with Antigravity & CatBoost

Pocket Data Science II: Tackling Kaggle Spaceship Titanic on Android with Antigravity & CatBoost

Comments
7 min read
Image prompting lessons: stop describing the image, hand the model a reference sheet

Image prompting lessons: stop describing the image, hand the model a reference sheet

Comments 1
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.